modelstatus.dev

Hy3

tencent/hy3

Compare with Hy3 preview, Hunyuan A13B Instruct, GLM 5.2

CompareHy3
  • Healthy24h 99.60%
    p50
    1.53s
    p99
    5.28s
    Throughput
    103 tps
    Context
    262K
    $/Mtok
    $0.200 / $0.800
    atlas-cloud/fp8fp8
  • Baidu100%
    Healthy24h 99.54%
    p50
    1.80s
    p99
    9.19s
    Throughput
    56 tps
    Context
    262K
    $/Mtok
    $0.132 / $0.528
    baidu/fp8fp8
  • Healthy24h 99.01%
    p50
    2.55s
    p99
    50.2s
    Throughput
    29 tps
    Context
    262K
    $/Mtok
    $0.126 / $0.522
    gmicloud/bf16bf16
  • Novita100%
    Healthy24h 99.28%
    p50
    3.14s
    p99
    9.73s
    Throughput
    57 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.580
    novita
  • Tencent99.95%
    Healthy24h 99.82%
    p50
    2.90s
    p99
    11.6s
    Throughput
    61 tps
    Context
    262K
    $/Mtok
    $0.132 / $0.528
    tencent/fp8fp8
  • DeepInfra97.45%
    Healthy24h 98.29%
    p50
    670ms
    p99
    44.1s
    Throughput
    55 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.580
    deepinfra/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.